Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    As

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    自救
    -0.07
    公办
    -0.07
    住户
    -0.07
    Male
    -0.07
    opy
    -0.07
     cheated
    -0.07
    fieldName
    -0.07
     southeastern
    -0.07
     kenn
    -0.07
    civil
    -0.07
    POSITIVE LOGITS
    _TCP
    0.06
    0.06
     columnist
    0.06
    ▢
    0.06
    いただき
    0.06
    ︰
    0.06
     Louisville
    0.06
     GPIO
    0.06
    �
    0.06
    appoint
    0.06
    Act Density 0.004%

    No Known Activations